Back

OpenClaw / Score

See which models score best on the OpenClaw task set.

UpdatedJun 12, 2026, 6:42 PM
MethodPublished benchmark snapshot
Rank Model Score Success rateSubmissionsTimeBest timeLowest cost Summary
#1
Claude Opus 4.8 Fast Anthropic
93.49% 94.49%505/29, 04:268582.96s$159.60 OpenClaw standard task average score 93.49%, success rate 94.49%.
#2
Qwen3.7 Max Qwen
92.51% 93.44%605/28, 02:5411253.57s$19.43 OpenClaw standard task average score 92.51%, success rate 93.44%.
#3
Claude Opus 4.8 Anthropic
90.54% 91.76%505/29, 05:5614327.32s$80.10 OpenClaw standard task average score 90.54%, success rate 91.76%.
#4
Nemotron 3 Ultra 550b A55b Nvidia
89.92% 90.58%505/29, 00:098110.08s$0.00 OpenClaw standard task average score 89.92%, success rate 90.58%.
#5
Mimo V2.5 Xiaomi
89.68% 91.87%605/30, 10:3810784.12s$5.44 OpenClaw standard task average score 89.68%, success rate 91.87%.
#6
Grok Build 0.1 X Ai
88.89% 92.07%505/24, 12:0312515.74s$19.03 OpenClaw standard task average score 88.89%, success rate 92.07%.
#7
Qwen3.6 Flash Qwen
88.09% 89.14%505/28, 02:5513016.06s$12.59 OpenClaw standard task average score 88.09%, success rate 89.14%.
#8
Mimo V2.5 Pro Xiaomi
87.45% 89.52%605/30, 11:3913280.66s$11.39 OpenClaw standard task average score 87.45%, success rate 89.52%.
#9
Ling 2.6 1t Inclusionai
82.64% 82.64%105/12, 03:2414396.79s$7.00 OpenClaw standard task average score 82.64%, success rate 82.64%.
#10
Deepseek V4 Flash Deepseek
81.74% 91.46%705/30, 10:4010894.73s$0.88 OpenClaw standard task average score 81.74%, success rate 91.46%.
#1
Claude Opus 4.8 Fast Anthropic
Score 93.49%
Success rate 94.49% · Best time 8582.96s

OpenClaw standard task average score 93.49%, success rate 94.49%.

#2
Qwen3.7 Max Qwen
Score 92.51%
Success rate 93.44% · Best time 11253.57s

OpenClaw standard task average score 92.51%, success rate 93.44%.

#3
Claude Opus 4.8 Anthropic
Score 90.54%
Success rate 91.76% · Best time 14327.32s

OpenClaw standard task average score 90.54%, success rate 91.76%.

#4
Nemotron 3 Ultra 550b A55b Nvidia
Score 89.92%
Success rate 90.58% · Best time 8110.08s

OpenClaw standard task average score 89.92%, success rate 90.58%.

#5
Mimo V2.5 Xiaomi
Score 89.68%
Success rate 91.87% · Best time 10784.12s

OpenClaw standard task average score 89.68%, success rate 91.87%.

#6
Grok Build 0.1 X Ai
Score 88.89%
Success rate 92.07% · Best time 12515.74s

OpenClaw standard task average score 88.89%, success rate 92.07%.

#7
Qwen3.6 Flash Qwen
Score 88.09%
Success rate 89.14% · Best time 13016.06s

OpenClaw standard task average score 88.09%, success rate 89.14%.

#8
Mimo V2.5 Pro Xiaomi
Score 87.45%
Success rate 89.52% · Best time 13280.66s

OpenClaw standard task average score 87.45%, success rate 89.52%.

#9
Ling 2.6 1t Inclusionai
Score 82.64%
Success rate 82.64% · Best time 14396.79s

OpenClaw standard task average score 82.64%, success rate 82.64%.

#10
Deepseek V4 Flash Deepseek
Score 81.74%
Success rate 91.46% · Best time 10894.73s

OpenClaw standard task average score 81.74%, success rate 91.46%.